tempmail_sdk 1.3.3 → 1.3.4

data/lib/tempmail_sdk/providers/mailgolem.rb

@@ -0,0 +1,96 @@
+# frozen_string_literal: true
+
+require "uri"
+
+module TempmailSdk
+  module Providers
+    # mailgolem.com 渠道实现
+    #
+    # 流程：GET / 获取 session cookie + CSRF token → GET /random-email-address 创建邮箱
+    #       GET / 重新获取 session + CSRF → POST /fetch-emails/{email} 获取邮件列表
+    # token 存储 CSRF token 值（收信时重新建立 session）
+    module Mailgolem
+      CHANNEL = "mailgolem"
+      BASE_URL = "https://mailgolem.com"
+
+      BROWSER_HEADERS = {
+        "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 " \
+                        "(KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0",
+        "Accept" => "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif," \
+                    "image/webp,image/apng,*/*;q=0.8",
+        "Accept-Language" => "en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7"
+      }.freeze
+
+      CSRF_RE = /<input[^>]+name="_token"[^>]+id="token"[^>]+value="([^"]*)"/im
+
+      module_function
+
+      # 从首页 HTML 提取 CSRF token
+      # @param html [String]
+      # @return [String]
+      def extract_csrf(html)
+        m = html.match(CSRF_RE)
+        m ? m[1].strip : ""
+      end
+
+      # 访问首页建立 session 并提取 CSRF token
+      # @return [String] csrf token
+      def fetch_csrf
+        resp = Http.get(BASE_URL + "/", headers: BROWSER_HEADERS, timeout: 15)
+        resp.raise_for_status
+        csrf = extract_csrf(resp.body)
+        raise "mailgolem: 未能从首页提取 CSRF token" if csrf.empty?
+
+        csrf
+      end
+
+      # 创建 mailgolem.com 临时邮箱
+      # @return [EmailInfo]
+      def generate_email
+        csrf = fetch_csrf
+        resp = Http.get(
+          BASE_URL + "/random-email-address",
+          headers: BROWSER_HEADERS.merge("Referer" => BASE_URL + "/"),
+          timeout: 15
+        )
+        resp.raise_for_status
+        email = resp.body.to_s.strip
+        raise "mailgolem: 获取到的邮箱地址无效" if email.empty? || !email.include?("@")
+
+        EmailInfo.new(channel: CHANNEL, email: email, token: csrf)
+      end
+
+      # 获取 mailgolem.com 邮件列表
+      # @param email [String]
+      # @param token [String] 旧 CSRF token（收信时重新建立 session）
+      # @return [Array<Email>]
+      def get_emails(email, token)
+        _ = token
+        csrf = fetch_csrf
+        form = URI.encode_www_form("_token" => csrf)
+        fetch_url = "#{BASE_URL}/fetch-emails/#{URI.encode_uri_component(email)}"
+        resp = Http.post(
+          fetch_url,
+          headers: BROWSER_HEADERS.merge(
+            "Content-Type" => "application/x-www-form-urlencoded",
+            "X-Requested-With" => "XMLHttpRequest",
+            "Accept" => "application/json, text/plain, */*",
+            "Referer" => BASE_URL + "/",
+            "Origin" => BASE_URL
+          ),
+          body: form,
+          timeout: 15
+        )
+        resp.raise_for_status
+        items = resp.json
+        return [] unless items.is_a?(Array)
+
+        items.filter_map do |item|
+          next unless item.is_a?(Hash)
+
+          Normalize.normalize_email(item.merge("to" => email), email)
+        end
+      end
+    end
+  end
+end

data/lib/tempmail_sdk/providers/mailinator.rb

@@ -136,13 +136,20 @@ module TempmailSdk
 
       # 将邮件摘要与正文/附件展平为 normalize 可识别的字段
       def flatten_message(summary, recipient_email, text_payload, html_payload, att_payload)
+        # 优先读 "text" 键（/text 端点实际返回键），回退兜底 "text/plain"（防御性编程）
+        text_content = text_from_payload(text_payload, "text")
+        text_content = text_from_payload(text_payload, "text/plain") if text_content.empty?
+        # 优先读 "html" 键，回退兜底 "text/html"
+        html_content = text_from_payload(html_payload, "html")
+        html_content = text_from_payload(html_payload, "text/html") if html_content.empty?
+
         {
           "id" => (summary["id"] || summary["messageId"] || "").to_s,
           "from" => first_non_empty(summary["from"], summary["origfrom"]),
           "to" => summary["to"] || recipient_email,
           "subject" => summary["subject"] || "",
-          "text" => text_from_payload(text_payload, "text/plain"),
-          "html" => text_from_payload(html_payload, "text/html"),
+          "text" => text_content,
+          "html" => html_content,
           "date" => to_iso_time(summary["time"] || summary["date"]),
           "seen" => false,
           "attachments" => build_attachments(att_payload)

data/lib/tempmail_sdk/providers/mailtemp_cc.rb

@@ -0,0 +1,91 @@
+# frozen_string_literal: true
+
+require "uri"
+
+module TempmailSdk
+  module Providers
+    # mailtemp.cc 渠道实现（PHP POST form-urlencoded API）
+    #
+    # 流程：POST api.php body: action=inbox 创建邮箱（返回 JSON 字符串用户名）
+    #       POST api.php body: action=fetch&inbox={username}&last_id=0 获取邮件列表
+    #       POST api.php body: action=view&id={id}&inbox={username} 获取邮件详情
+    # token 存储 username（@前面的部分），域名固定 neocea.com
+    module MailtempCc
+      CHANNEL = "mailtemp-cc"
+      API_URL = "https://mailtemp.cc/api.php"
+
+      HEADERS = {
+        "Content-Type" => "application/x-www-form-urlencoded",
+        "Accept" => "application/json, text/plain, */*",
+        "Accept-Language" => "zh-CN,zh;q=0.9,en;q=0.8",
+        "Referer" => "https://mailtemp.cc/",
+        "Origin" => "https://mailtemp.cc",
+        "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 " \
+                        "(KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0"
+      }.freeze
+
+      module_function
+
+      # 创建 mailtemp.cc 临时邮箱
+      # @return [EmailInfo]
+      def generate_email
+        resp = Http.post(API_URL, headers: HEADERS, body: "action=inbox", timeout: 15)
+        resp.raise_for_status
+        # 返回值为 JSON 字符串格式（带引号），如 "vindictiverate"
+        username = resp.json
+        username = username.to_s.strip
+        raise "mailtemp-cc: 返回的用户名为空" if username.empty?
+
+        EmailInfo.new(channel: CHANNEL, email: "#{username}@neocea.com", token: username)
+      end
+
+      # 获取 mailtemp.cc 邮件列表
+      # @param email [String]
+      # @param token [String] username
+      # @return [Array<Email>]
+      def get_emails(email, token)
+        token = token.to_s.strip
+        raise "mailtemp-cc: token 为空" if token.empty?
+
+        form = URI.encode_www_form("action" => "fetch", "inbox" => token, "last_id" => "0")
+        resp = Http.post(API_URL, headers: HEADERS, body: form, timeout: 15)
+        resp.raise_for_status
+        items = resp.json
+        return [] unless items.is_a?(Array)
+        return [] if items.empty?
+
+        items.filter_map do |item|
+          next unless item.is_a?(Hash)
+
+          mail_id = item["id"].to_s
+          unless mail_id.empty?
+            detail = view_email(token, mail_id)
+            if detail.is_a?(Hash)
+              item["html"] = detail["body_html"] if detail["body_html"]
+              item["body_html"] = detail["body_html"] if detail["body_html"]
+            end
+          end
+
+          item["from"] ||= item["sender_email"] || item["sender"]
+          item["date"] ||= item["received_at"]
+          item["to"] = email
+          Normalize.normalize_email(item, email)
+        end
+      end
+
+      # 获取单封邮件详情
+      # @param inbox [String] username
+      # @param mail_id [String]
+      # @return [Hash, nil]
+      def view_email(inbox, mail_id)
+        form = URI.encode_www_form("action" => "view", "id" => mail_id, "inbox" => inbox)
+        resp = Http.post(API_URL, headers: HEADERS, body: form, timeout: 15)
+        return nil unless resp.ok?
+
+        resp.json
+      rescue StandardError
+        nil
+      end
+    end
+  end
+end

data/lib/tempmail_sdk/providers/minuteinbox.rb

@@ -0,0 +1,174 @@
+# frozen_string_literal: true
+
+require "json"
+require "uri"
+
+module TempmailSdk
+  module Providers
+    # minuteinbox.com 渠道实现（PHP session + CSRF token）
+    #
+    # 流程：GET / 获取 PHPSESSID cookie 和 CSRF token（const CSRF="xxx"）
+    #       GET /index/index?csrf_token={csrf} 创建邮箱，返回 {"email":"user@minafter.com"}
+    #       GET /index/refresh 获取邮件列表
+    #       POST /index/email body: id=X 获取邮件详情
+    # token 存储 JSON {"phpsessid":"...","csrf":"..."}
+    module Minuteinbox
+      CHANNEL = "minuteinbox"
+      BASE_URL = "https://www.minuteinbox.com"
+
+      module_function
+
+      # 从 HTML 中提取 CSRF token（格式: const CSRF="xxx"）
+      # @param html [String]
+      # @return [String]
+      def extract_csrf(html)
+        marker = 'CSRF="'
+        idx = html.index(marker)
+        return "" unless idx
+
+        sub = html[(idx + marker.length)..]
+        end_idx = sub.index('"')
+        end_idx ? sub[0...end_idx] : ""
+      end
+
+      # 将 session 序列化为 JSON token
+      # @param phpsessid [String]
+      # @param csrf [String]
+      # @return [String]
+      def encode_session(phpsessid, csrf)
+        JSON.generate("phpsessid" => phpsessid, "csrf" => csrf)
+      end
+
+      # 从 JSON token 反序列化 session
+      # @param token [String]
+      # @return [Array<String>] [phpsessid, csrf]
+      def decode_session(token)
+        data = JSON.parse(token)
+        phpsessid = data["phpsessid"].to_s.strip
+        csrf = data["csrf"].to_s.strip
+        raise "minuteinbox: session token 缺少必要字段" if phpsessid.empty? || csrf.empty?
+
+        [phpsessid, csrf]
+      rescue JSON::ParserError
+        raise "minuteinbox: 无效的 session token"
+      end
+
+      # 创建 minuteinbox.com 临时邮箱
+      # @return [EmailInfo]
+      def generate_email
+        hdrs = {
+          "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 " \
+                          "(KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0",
+          "Accept" => "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
+        }
+        r1 = Http.get(BASE_URL + "/", headers: hdrs, timeout: 15)
+        r1.raise_for_status
+
+        csrf = extract_csrf(r1.body)
+        raise "minuteinbox: 未能从首页提取 CSRF token" if csrf.empty?
+
+        phpsessid = ""
+        r1.set_cookies.each do |line|
+          pair = line.split(";", 2).first.to_s.strip
+          next unless pair.start_with?("PHPSESSID=")
+
+          phpsessid = pair.split("=", 2).last.to_s.strip
+          break
+        end
+        raise "minuteinbox: 未获取到 PHPSESSID cookie" if phpsessid.empty?
+
+        create_url = "#{BASE_URL}/index/index?csrf_token=#{URI.encode_uri_component(csrf)}"
+        r2 = Http.get(
+          create_url,
+          headers: hdrs.merge(
+            "X-Requested-With" => "XMLHttpRequest",
+            "Cookie" => "PHPSESSID=#{phpsessid}"
+          ),
+          timeout: 15
+        )
+        r2.raise_for_status
+
+        data = r2.json
+        email = data.is_a?(Hash) ? data["email"].to_s.strip : ""
+        raise "minuteinbox: 获取到的邮箱地址无效" if email.empty? || !email.include?("@")
+
+        EmailInfo.new(channel: CHANNEL, email: email, token: encode_session(phpsessid, csrf))
+      end
+
+      # 获取 minuteinbox.com 邮件列表
+      # @param token [String] JSON session token
+      # @param email [String]
+      # @return [Array<Email>]
+      def get_emails(token, email)
+        phpsessid, _csrf = decode_session(token)
+        cookie_hdr = "PHPSESSID=#{phpsessid}"
+        hdrs = {
+          "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 " \
+                          "(KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0",
+          "X-Requested-With" => "XMLHttpRequest",
+          "Cookie" => cookie_hdr
+        }
+
+        r = Http.get(BASE_URL + "/index/refresh", headers: hdrs, timeout: 15)
+        r.raise_for_status
+
+        trimmed = r.body.to_s.strip
+        return [] if trimmed == "0" || trimmed.empty? || trimmed == "[]"
+
+        mail_list = r.json
+        return [] unless mail_list.is_a?(Array) && !mail_list.empty?
+
+        mail_list.filter_map do |item|
+          next unless item.is_a?(Hash)
+
+          mail_id = item["id"].to_s
+          detail = fetch_detail(cookie_hdr, mail_id) unless mail_id.empty?
+
+          is_read = item["precteno"] != "new"
+          from = detail&.dig("od") || item["od"] || ""
+          subject = detail&.dig("predmet") || item["predmet"] || ""
+          html_body = detail&.dig("telo") || ""
+          to = detail&.dig("komu") || email
+
+          flat = {
+            "id" => mail_id,
+            "from" => from,
+            "to" => to,
+            "subject" => subject,
+            "html" => html_body,
+            "date" => item["kdy"] || "",
+            "isRead" => is_read
+          }
+          Normalize.normalize_email(flat, email)
+        end
+      end
+
+      # 获取单封邮件详情
+      # @param cookie_hdr [String]
+      # @param mail_id [String]
+      # @return [Hash, nil]
+      def fetch_detail(cookie_hdr, mail_id)
+        return nil if mail_id.empty?
+
+        hdrs = {
+          "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 " \
+                          "(KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0",
+          "X-Requested-With" => "XMLHttpRequest",
+          "Content-Type" => "application/x-www-form-urlencoded",
+          "Cookie" => cookie_hdr
+        }
+        resp = Http.post(
+          BASE_URL + "/index/email",
+          headers: hdrs,
+          body: "id=#{URI.encode_uri_component(mail_id)}",
+          timeout: 15
+        )
+        return nil unless resp.ok?
+
+        resp.json
+      rescue StandardError
+        nil
+      end
+    end
+  end
+end

data/lib/tempmail_sdk/providers/moakt.rb

@@ -42,7 +42,7 @@ module TempmailSdk
       TITLE_RE = /<li\s+class="title"\s*>([^<]*)<\/li>/im
       DATE_RE = /<li\s+class="date"[^>]*>[\s\S]*?<span[^>]*>([^<]+)<\/span>/im
       SENDER_RE = /<li\s+class="sender"[^>]*>[\s\S]*?<span[^>]*>([\s\S]*?)<\/span>\s*<\/li>/im
-      BODY_RE = /<div\s+class="email-body"\s*>([\s\S]*?)<\/div>/im
+      BODY_OPEN_RE = /<div\s+class="email-body"\s*>/im
       FROM_ADDR_RE = /<([a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,})>/
       TAG_RE = /<[^>]+>/
 
@@ -161,6 +161,33 @@ module TempmailSdk
         addr
       end
 
+      # 使用栈式深度匹配提取 email-body div 的完整内部 HTML，
+      # 避免非贪婪正则在嵌套 div 时截断正文。
+      def extract_body_html(page)
+        m = page.match(BODY_OPEN_RE)
+        return "" unless m
+
+        start = m.end(0)
+        pos = start
+        depth = 1
+        while pos < page.length && depth > 0
+          next_open = page.index("<div", pos)
+          next_close = page.index("</div>", pos)
+          break unless next_close
+
+          if next_open && next_open < next_close
+            depth += 1
+            pos = next_open + 4
+          else
+            depth -= 1
+            return page[start...next_close].strip if depth.zero?
+
+            pos = next_close + 6
+          end
+        end
+        ""
+      end
+
       # 去除 HTML 标签，压缩为文本
       def strip_tags(s)
         s.gsub(TAG_RE, " ").strip
@@ -200,8 +227,7 @@ module TempmailSdk
         date_s = ""
         date_s = CGI.unescapeHTML(page.match(DATE_RE)[1].strip) if page.match?(DATE_RE)
 
-        body = ""
-        body = page.match(BODY_RE)[1].strip if page.match?(BODY_RE)
+        body = extract_body_html(page)
 
         {
           "id" => mid,

data/lib/tempmail_sdk/providers/mohmal.rb

@@ -0,0 +1,208 @@
+# frozen_string_literal: true
+
+require "cgi"
+
+module TempmailSdk
+  module Providers
+    # mohmal.com 渠道实现（HTML 页面解析，session cookie）
+    #
+    # 流程：GET /en/create/random 创建邮箱（跟随重定向到 /en/inbox），从 data-email 属性提取邮箱地址
+    #       GET /en/inbox 解析邮件链接列表
+    #       GET /en/message/{id}/html 获取邮件详情
+    # token 存储 connect.sid cookie 字符串
+    # 注意：正文提取使用栈式深度匹配，避免非贪婪正则截断嵌套 div
+    module Mohmal
+      CHANNEL = "mohmal"
+      BASE_URL = "https://www.mohmal.com"
+
+      DATA_EMAIL_RE = /data-email=["']([^"']+)["']/im
+      MSG_HREF_RE = /href=["'](\/en\/message\/([^"']+))["']/i
+      DETAIL_FROM_RE = /<span[^>]+class=["'][^"']*from[^"']*["'][^>]*>([\s\S]*?)<\/span>/im
+      DETAIL_SUBJECT_RE = /<span[^>]+class=["'][^"']*subject[^"']*["'][^>]*>([\s\S]*?)<\/span>/im
+      DETAIL_DATE_RE = /<span[^>]+class=["'][^"']*date[^"']*["'][^>]*>([\s\S]*?)<\/span>/im
+      TAG_RE = /<[^>]+>/
+      BODY_OPEN_RE = /<div\s+class=["'][^"']*(?:mail-body|message-body|message_body)[^"']*["']\s*>/im
+
+      BROWSER_HEADERS = {
+        "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 " \
+                        "(KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0",
+        "Accept" => "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif," \
+                    "image/webp,image/apng,*/*;q=0.8",
+        "Accept-Language" => "en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7",
+        "Cache-Control" => "no-cache",
+        "DNT" => "1",
+        "Pragma" => "no-cache",
+        "Upgrade-Insecure-Requests" => "1"
+      }.freeze
+
+      module_function
+
+      # 从 HTML 中提取 data-email 属性值
+      # @param html [String]
+      # @return [String]
+      def extract_email(html)
+        m = html.match(DATA_EMAIL_RE)
+        m ? CGI.unescapeHTML(m[1].strip) : ""
+      end
+
+      # 合并 Cookie 头与响应 Set-Cookie
+      # @param existing [String]
+      # @param set_cookie_lines [Array<String>]
+      # @return [String]
+      def merge_cookies(existing, set_cookie_lines)
+        map = {}
+        existing.to_s.split(";").each do |part|
+          part = part.strip
+          next unless part.include?("=")
+
+          k, v = part.split("=", 2)
+          map[k.strip] = v.to_s.strip unless k.strip.empty?
+        end
+        set_cookie_lines.each do |line|
+          pair = line.split(";", 2).first.to_s.strip
+          next unless pair.include?("=")
+
+          k, v = pair.split("=", 2)
+          map[k.strip] = v.to_s.strip unless k.strip.empty?
+        end
+        map.map { |k, v| "#{k}=#{v}" }.join("; ")
+      end
+
+      # 去除 HTML 标签并修剪空白
+      # @param s [String]
+      # @return [String]
+      def strip_tags(s)
+        s.gsub(TAG_RE, " ").strip
+      end
+
+      # 使用栈式深度匹配提取指定 class 的 div 完整内部 HTML
+      # 避免非贪婪正则在嵌套 div 时截断正文
+      # @param page [String]
+      # @return [String]
+      def extract_body_html(page)
+        m = page.match(BODY_OPEN_RE)
+        return "" unless m
+
+        start = m.end(0)
+        pos = start
+        depth = 1
+        while pos < page.length && depth > 0
+          next_open = page.index("<div", pos)
+          next_close = page.index("</div>", pos)
+          break unless next_close
+
+          if next_open && next_open < next_close
+            depth += 1
+            pos = next_open + 4
+          else
+            depth -= 1
+            return page[start...next_close].strip if depth.zero?
+
+            pos = next_close + 6
+          end
+        end
+        ""
+      end
+
+      # 创建 mohmal.com 临时邮箱
+      # @return [EmailInfo]
+      def generate_email
+        r1 = Http.get(
+          BASE_URL + "/en/create/random",
+          headers: BROWSER_HEADERS.merge("Referer" => BASE_URL + "/en"),
+          timeout: 15
+        )
+        r1.raise_for_status
+        cookie_hdr = merge_cookies("", r1.set_cookies)
+        email = extract_email(r1.body)
+
+        if email.empty?
+          r2 = Http.get(
+            BASE_URL + "/en/inbox",
+            headers: BROWSER_HEADERS.merge("Referer" => BASE_URL + "/en", "Cookie" => cookie_hdr),
+            timeout: 15
+          )
+          r2.raise_for_status
+          cookie_hdr = merge_cookies(cookie_hdr, r2.set_cookies)
+          email = extract_email(r2.body)
+        end
+
+        raise "mohmal: 未能从页面中提取邮箱地址" if email.empty?
+
+        EmailInfo.new(channel: CHANNEL, email: email, token: cookie_hdr)
+      end
+
+      # 获取 mohmal.com 邮件列表
+      # @param email [String]
+      # @param token [String] connect.sid cookie 字符串
+      # @return [Array<Email>]
+      def get_emails(email, token)
+        raise "mohmal: session cookie 为空" if token.to_s.strip.empty?
+
+        r = Http.get(
+          BASE_URL + "/en/inbox",
+          headers: BROWSER_HEADERS.merge(
+            "Referer" => BASE_URL + "/en",
+            "Cookie" => token
+          ),
+          timeout: 15
+        )
+        r.raise_for_status
+
+        seen = {}
+        msgs = []
+        r.body.scan(MSG_HREF_RE) do |path, id|
+          next if path.include?("/delete")
+          next if seen[id]
+
+          seen[id] = true
+          msgs << { path: path, id: id }
+        end
+        return [] if msgs.empty?
+
+        msgs.filter_map do |msg|
+          raw = fetch_detail(token, msg[:id], email)
+          Normalize.normalize_email(raw, email)
+        end
+      end
+
+      # 获取单封邮件详情页
+      # @param cookie [String]
+      # @param id [String]
+      # @param recipient [String]
+      # @return [Hash]
+      def fetch_detail(cookie, id, recipient)
+        raw = { "id" => id, "to" => recipient }
+        detail_url = "#{BASE_URL}/en/message/#{id}/html"
+        resp = Http.get(
+          detail_url,
+          headers: BROWSER_HEADERS.merge(
+            "Referer" => "#{BASE_URL}/en/inbox",
+            "Cookie" => cookie
+          ),
+          timeout: 15
+        )
+        return raw unless resp.status_code == 200
+
+        page = resp.body
+
+        if (m = page.match(DETAIL_FROM_RE))
+          raw["from"] = strip_tags(CGI.unescapeHTML(m[1])).strip
+        end
+        if (m = page.match(DETAIL_SUBJECT_RE))
+          raw["subject"] = CGI.unescapeHTML(strip_tags(m[1])).strip
+        end
+        if (m = page.match(DETAIL_DATE_RE))
+          raw["date"] = CGI.unescapeHTML(strip_tags(m[1])).strip
+        end
+
+        body_html = extract_body_html(page)
+        raw["html"] = body_html unless body_html.empty?
+
+        raw
+      rescue StandardError
+        raw
+      end
+    end
+  end
+end